TY - GEN
T1 - Deep multitask learning for semantic dependency parsing
AU - Peng, Hao
AU - Thomson, Sam
AU - Smith, Noah A.
N1 - Funding Information:
We thank the Ark, Maxwell Forbes, Luheng He, Kenton Lee, Julian Michael, and Jin-ge Yao for their helpful comments on an earlier version of this draft, and the anonymous reviewers for their valuable feedback. This work was supported by NSF grant IIS-1562364 and DARPA grant FA8750-12-2-0342 funded under the DEFT program.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches-one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.
AB - We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches-one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.
UR - http://www.scopus.com/inward/record.url?scp=85040928896&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85040928896&partnerID=8YFLogxK
U2 - 10.18653/v1/P17-1186
DO - 10.18653/v1/P17-1186
M3 - Conference contribution
AN - SCOPUS:85040928896
T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 2037
EP - 2048
BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Y2 - 30 July 2017 through 4 August 2017
ER -